Issue with the generate_fashion_datasets.py

[S-Ahmed89]

Hi,

Thanks for the great work! I am going to train according to the guideline you mentioned. But having couple of issues as below while trying:

1. When run train.py with the full command using Market1501 data (!python train.py --dataroot ./market_data/ --name market_PATN --model PATN --lambda_GAN 5 --lambda_A 10 --lambda_B 10 --dataset_mode keypoint --no_lsgan --n_layers 3 --norm batch --batchSize 32 --resize_or_crop no --gpu_ids 0 --BP_input_nc 18 --no_flip --which_model_netG PATN --niter 500 --niter_decay 200 --checkpoints_dir ./checkpoints --pairLst ./market_data/market-pairs-train.csv --L1_type l1_plus_perL1 --n_layers_D 3 --with_D_PP 1 --with_D_PB 1 --display_id 0) the training is continuing for more than 20 hours with . I am running it on a laptop with NVIDIA GPU. Is it normal?

2. When running the command: python tool/generate_fashion_datasets.py I face the attached issue.

Could you please help me fixing the issue? Thanks and best regards, Sabbir

[llll5555]

我也遇到了同样的问题，而且数据集分成train和test时，文件夹下没有图片